INDEX

Explanations

terms related to cost and sharing

oai_token-act-pair · gpt-3.5-turbo

phrases related to cost and effectiveness

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Pod

-0.67

 Crescent

-0.65

Klu

-0.63

 Shirt

-0.63

 borough

-0.63

KN

-0.62

 Bake

-0.62

 Kern

-0.62

ulhu

-0.61

 Airways

-0.61

POSITIVE LOGITS

effective

1.20

benefit

1.20

efficient

1.20

adjusted

1.19

free

1.10

saving

1.07

efficiency

1.07

sensitive

1.06

resistant

1.04

adjust

1.03

Activations Density 0.080%

terms related to cost and sharing

phrases related to cost and effectiveness

No Comments

No Known Activations